Add Qwen2 GGUF loading support

[Isotr0py]

What does this PR do?

• Add Qwen2 GGUF loading support
• Use model_type for gguf tokenizer converter selection instead of tokenizer_type

According to convert-hf-to-gguf.py, most of models may register tokenizer as gpt2 tokenizer. Use model_type to select corresponding tokenizer instead of tokenizer_type.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[younesbelkada]

Thanks a lot for this great contribution ! Can you confirm the other slow tests pass ? 🙏 I left few minor comments, what do you think?

[younesbelkada]

Great work ! Thanks for adding Qwen2 support for GGUF files ! Can you run the styling checks? make fixup after that this PR is ready IMO

[amyeroberts]

Thanks for adding!